Local shape descriptors for neuron segmentation.

Our Research / Publications

janelia7_blocks-janelia7_biblio_header | block

Nature Methods. 2023 Feb 01;20(2):295-303. doi: 10.1038/s41592-022-01711-z

View Article on

Local shape descriptors for neuron segmentation. Saalfeld LabTuraga LabFunke Lab

Sheridan A, Nguyen TM, Deb D, Lee WA, Saalfeld S, Turaga SC, Manor U, Funke J

janelia7_blocks-janelia7_biblio_abstract | block

Abstract

We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a study comparing several existing methods across various specimen, imaging techniques, and resolutions, auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinity-based segmentation methods to be on par with the current state of the art for neuron segmentation (flood-filling networks), while being two orders of magnitudes more efficient-a critical requirement for the processing of future petabyte-sized datasets.

PMID: 36585455 [PubMed - indexed for MEDLINE]

janelia7_blocks-janelia7_biblio_authors | block

janelia7_blocks-janelia7_biblio_tools | block

Main Menu (Mobile)- Block

Main Menu - Block

Local shape descriptors for neuron segmentation.

Abstract

PMID: 36585455 [PubMed - indexed for MEDLINE]

Janelia Authors